A Python library to train task-specific LLMs without training data, for offline NLP and Text Classification tasks, such as Guardrail Models and Intent Classification π€π
Source code for grammar-based text-to-SQL parser using one variant of Transformer decoder called ASTormer. Implementations for prevalent cross-domain multi-table benchmarks Spider, SParC, CoSQL, DuSQL and Chase are all included.
[TPAMI2023] A Heterogeneous Graph to Abstract Syntax Tree Framework for Text-to-SQL
End-to-end portfolio construction systems exemplify modern quantitative investing where machine learning and optimization are tightly coupled to drive better portfolio outcomes. This repository contains a Jupyter notebook that illustrates a mean-variance end-to-end system and compares it to bechmark models.
Add a description, image, and links to the task-specific-model topic page so that developers can more easily learn about it.
To associate your repository with the task-specific-model topic, visit your repo's landing page and select "manage topics."